Agent skill
aider
AI pair-programming tool that allows you to code with LLMs directly in your terminal and Git repository. Core Scenario: When the user wants to collaborate with an AI on code modifications, automated commits, or whole-repo context tasks.
Install this agent skill to your Project
npx add-skill https://github.com/x-cmd/skill/tree/main/data/x-cmd/aider
SKILL.md
aider - AI Pair-Programming in Terminal
aider is an AI pair-programming tool that enables developers to collaborate with high-end LLMs (Claude 3.7, DeepSeek R1, GPT-4o, etc.) directly in the terminal. It understands entire Git repositories and can perform multi-file changes and automated commits.
When to Activate
- When the user wants to start an AI-assisted pair-programming session.
- When performing complex code refactoring or modifications across multiple files.
- When the user needs automated, semantic Git commit messages for AI-generated changes.
- When utilizing "Voice-to-Code" or embedding external content (screenshots/webpages) into the coding context.
Core Principles & Rules
- Git Integration: Aider is most effective when run inside a Git repository.
- Model Versatility: Supports a wide range of models (Claude, DeepSeek, OpenAI, local LLMs).
- Automation: Can automatically run lints and tests to verify changes.
Additional Scenarios
- Whole-Repo Context: Automatically generates a map of the repository to help the LLM understand complex architectures.
- Multi-File Editing: Seamlessly handles modifications that span multiple source files.
Patterns & Examples
Launch Aider
# Start an interactive pair-programming session
x aider
Checklist
- Verify that the user is inside a Git repository for optimal performance.
- Confirm the target LLM is configured and accessible.
- Check if additional dependencies (like for voice input) are needed.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
pufferlib
High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.
fluidsim
Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D), shallow water equations, stratified flows, or when analyzing turbulence, vortex dynamics, or geophysical flows. Provides pseudospectral methods with FFT, HPC support, and comprehensive output analysis.
metabolomics-workbench-database
Access NIH Metabolomics Workbench via REST API (4,200+ studies). Query metabolites, RefMet nomenclature, MS/NMR data, m/z searches, study metadata, for metabolomics and biomarker discovery.
geniml
This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.
zinc-database
Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.
astropy
Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.
Didn't find tool you were looking for?